Training in progress, step 3900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a4cdfe8e0c7797aa7c57c96550731ad9d42021cfaedb244e4aed3242ed4703
+oid sha256:2c66c167440aeb0946d6279663e50d9312ceb473cdcf6f29f4160f36a159995c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b537fe08e3bd2d91fabd801c9bfd329d7b41b9f47ce7392a352be7bccb9544
+oid sha256:5e556816dc43ae052927f85f00760ef86b74653fc28d4c08a26ef67b4c14e5be
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cff68ccfd4b7f7441d9d6f3e2f7132d2890a46c56e8f2f0a975fd95b0cd6b66c
+oid sha256:4f387f966aecfa76017d726e43b1fa9c3ccecd8af5742b255e2ef66c7eeb645b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
+oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.081820011138916,
-  "best_model_checkpoint": "./outputs/checkpoint-3800",
-  "epoch": 2.768670309653916,
+  "best_metric": 2.069366693496704,
+  "best_model_checkpoint": "./outputs/checkpoint-3900",
+  "epoch": 2.841530054644809,
   "eval_steps": 100,
-  "global_step": 3800,
+  "global_step": 3900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -539,13 +539,27 @@
       "eval_samples_per_second": 30.51,
       "eval_steps_per_second": 3.817,
       "step": 3800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002,
+      "loss": 2.0329,
+      "step": 3900
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 2.069366693496704,
+      "eval_runtime": 205.3899,
+      "eval_samples_per_second": 30.547,
+      "eval_steps_per_second": 3.822,
+      "step": 3900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0818983291332608e+17,
+  "total_flos": 1.1105217882630144e+17,
   "trial_name": null,
   "trial_params": null
 }